DeepEnhancer

[Dan64]

I was able to use this package.

I had to create an environment with the following packages

# Name                    Version
albumentations            2.0.5
matplotlib                3.10.1
mmcv                      2.2.0
mmcv-full                 1.7.2
numpy                     2.1.2
nvidia-cuda-runtime-cu12  12.8.90
opencv-python             4.11.0.86
opencv-python-headless    4.11.0.86
pillow                    11.0.0
pip                       25.0
scikit-image              0.25.2
scipy                     1.15.2
setuptools                75.8.0
tensorrt                  10.9.0.34
tensorrt-cu12             10.9.0.34
tensorrt-cu12-bindings    10.9.0.34
tensorrt-cu12-libs        10.9.0.34
torch                     2.8.0.dev20250314+cu128
torchaudio                2.6.0.dev20250315+cu128
torchvision               0.22.0.dev20250315+cu128

I don't know in Linux what happens, but in window, running the demo I get out-of-memory error, despite the fact that I have a 16GB GPU.

So I had to reduce the size of frames in input to get this package working in Windows.

The coloring capability are very bad (see picture below)



Probably the model was trained to coloring well only the clip provided as demo.

The restoring part is better, but in my opinion in Hybrid there are better tool.

I attached some clips restored using DeepEnhancer, BasicVSR++ (Video Denoising) and BasicVSR++ (NTIRE 2021 (3))

In my opinion BasicVSR++ (NTIRE 2021 (3)) is better.

I have no intention of spending any more time on this project.

Dan